FrozenGene commented on code in PR #14886:
URL: https://github.com/apache/tvm/pull/14886#discussion_r1198555736
##########
python/tvm/relay/frontend/pytorch.py:
##########
@@ -5005,3 +5006,180 @@ def from_pytorch(
export_c_graph(export_renamed_c_graph_path, graph)
return transform.RemoveUnusedFunctions()(mod), tvm_params
+
+
+def tvm_relay_backend(gm, example_inputs, *, scheduler=None, trials=20000):
Review Comment:
It is better to add VM backend too.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
